Add llama.cpp serving command alongside vLLM

The serving section documented only vLLM's --reasoning-parser qwen3. Compact is the llama.cpp release, and llama.cpp users had no documented equivalent for separating reasoning, which is required for multi-turn agent use.

README.md

@@ -70,6 +70,22 @@ vllm serve badtheorylabs/BTL-4 \
   --trust-remote-code
 ```
 
+llama.cpp, using the GGUF build:
+
+```bash
+llama-server -m BTL-4-IQ2_XXS.gguf --port 8080 \
+  --jinja \
+  --reasoning-format deepseek \
+  -c 32768 -fa on \
+  --cache-type-k q8_0 --cache-type-v q8_0
+```
+
+**Reasoning must be separated from content, on every stack.** The chat template
+strips reasoning from older turns, but only when the harness puts it in
+`reasoning_content`. With vLLM that is `--reasoning-parser qwen3`; with
+llama.cpp it is `--reasoning-format deepseek`. Without it, reasoning accumulates
+into `content` each turn and the model repeats turns instead of terminating.
+
 ### Generation settings
 
 Ornith's published settings, used for every number above: